Early detection of glaucoma: feature visualization with a deep convolutional network

Figures & data

Figure 1. Fundus image (a) healthy eye (b) glaucomatous eye (c) glaucomatous image marked by the expert.

Figure 2. Proposed deep CNN model with visualization of features.

Figure 3. Pre-processing of fundus image with glaucoma (a) entire image (b) fundus image cropped around OD (c) fundus glaucoma image cropped around ONH including RNFL region (d) segmented optic disc region.

Figure 4. Examples of the ROI in the fundus images cropped around the ONH including RNFL region for both normal and glaucomatous images.

Table 1. Fundus dataset before and after augmentation.

Fundus glaucoma class	Total images	Images after augmentation
Mild	10	50
Moderate	23	118
Severe	29	137

Figure 5. The proposed deep CNN architecture.

Table 2. Details of the proposed deep CNN architecture.

Layers	Kernels	Filter size	Output shape
Conv2D 1	32	3 x 3	254 x 254 x 32
MaxPool2D 1	32	2 x 2	127 x 127 x 32
Conv2D 2	64	3 x 3	125 x 125 x 64
MaxPool2D 2	64	2 x 2	62 x 62 x 64
Conv2D 3	128	3 x 3	60 x 60 x 128
MaxPool2D 3	128	2 x 2	30 x 30 x 128
Conv2D 4	256	3 x 3	28 x 28 x 256
MaxPool2D 4	256	2 x 2	14 x 14 x 256
Flatten	–	–	50176
Fully connected Dense1	256	–	256
Fully connected Dense2	2	–	2

Table 3. The list of hyperparameters for the ImageNet trained architectures.

Type of glaucoma	Network	Optimizer	Batch size	Learning rate	Epochs
Mild	VGG16	Adam	16	0.001	100
	ResNet50	Adam	16	0.001	100
	MobileNetV2	Adam	32	0.0001	50
	Proposed Deep CNN	RMSprop	16	0.0001	100
Moderate	VGG16	Adam	32	0.0001	100
	ResNet50	Adam	32	0.0001	100
	MobileNetV2	Adam	32	0.0001	100
	Proposed Deep CNN	RMSprop	16	0.0001	100
Severe	VGG16	Adam	32	0.0001	100
	ResNet50	Adam	32	0.0001	100
	MobileNetV2	Adam	32	0.0001	100
	Proposed Deep CNN	RMSprop	16	0.0001	100

Table 4. Total images used for training and testing the architecture.

Glaucoma classes	Glaucoma images	Normal images	Total
Mild	50	60	110
Moderate	118	120	238
Severe	137	140	277

Figure 6. Visualization of the feature maps of first layer of activation. The first row is a feature map of mild glaucoma, the second row is moderate glaucoma, and the third row is severe glaucoma. The feature maps are plotted for the 7^th and 16^th channels which are taken randomly out of the 32 channels in the first activation layer.

Figure 7. Accuracy curve and loss curve of mild glaucoma class.

Figure 8. Accuracy curve and loss curve of moderate glaucoma class.

Figure 9. Accuracy curve and loss curve of severe glaucoma class.

Table 5. Training and validation accuracy of glaucoma dataset.

Glaucoma class	Training accuracy	Validation accuracy	Training loss	Validation loss
Mild	85.71	87.88	0.31	0.36
Moderate	92.81	94.37	0.17	0.23
Severe	93.8	89.1	0.12	0.48

Figure 10. Confusion matrices for (a) mild glaucoma (b) moderate glaucoma (c) severe glaucoma.

Table 6. Results of performance metrics evaluated for the deep CNN architecture.

Glaucoma class	Accuracy (%)	Sensitivity (%)	Specificity (%)	Precision (%)	F1-score	MCC
Mild	93.75	100	87.5	88.8	0.94	+0.88
Moderate	100	100	100	100	1	+1
Severe	93.75	100	83.3	90.9	0.95	+0.87

Table 7. Comparison of result of test accuracy for proposed deep CNN model and ImageNet trained architectures.

Glaucoma	VGG16	ResNet50	MobileNetV2	Proposed deep CNN model
Class	Test Accuracy (%)	Test Accuracy (%)	Test Accuracy (%)	Test Accuracy (%)
Mild	84.09	81.82	75	93.75
Moderate	89.13	97.83	89.03	100
Severe	97.03	93.07	94.06	93.75

Table 8. Comparison of performance metrics evaluated for the existing models vs proposed model.

Model	ACC (%)	SE (%)	SP (%)	PRC (%)	F1-score	MCC
(Diaz-Pinto et al. 2019)	80.00	83.33	77.78	-	-	-
(Elangovan and Nath 2021)	96.64	96.07	97.39	97.74	-	-
(Li et al. 2020)	85.20	84.80	85.50	-	-	-
(Alghamdi et al. 2017)	86.52	96.42	86.00	-	-	-
Proposed	93.75	100	87.5	88.8	0.94	+0.88

Diaz-Pinto A, Morales S, Naranjo V, Köhler T, Mossi JM, Navea A. 2019. Cnns for automatic glaucoma assessment using fundus images: an extensive validation. Biomed Eng Online. 18(1):1–19. doi: 10.1186/s12938-019-0649-y.

 PubMed Web of Science ®Google Scholar

Elangovan P, Nath MK. 2021. Glaucoma assessment from color fundus images using convolutional neural network. Int J Imaging Syst Technol. 31(2):955–971. doi: 10.1002/ima.22494.

 Web of Science ®Google Scholar

Li L, Xu M, Liu H, Li Y, Wang X, Jiang L, Wang Z, Fan X, Wang N. 2020. A large-scale database and a CNN model for attention-based glaucoma detection. IEEE Trans Med Imaging. 39(2):413–424. doi: 10.1109/TMI.2019.2927226.

 PubMed Web of Science ®Google Scholar

Alghamdi HS, Tang HL, Waheeb SA, Peto T. 2017. Automatic optic disc abnormality detection in fundus images: a deep learning approach. 17–24. 10.17077/omia.1042.

 Google Scholar